Deep Learning Approaches for Microplastic Identification in Microscopic Water Samples

Read full text Summarise with VIRAT
Authors: J. Rajeswari, B. Naveen Kumar, S. Senthilrani, S. Amrudha, M. Annie Pushpa, S. Thamarai Natchiyar
Cited by: 0
References: 1

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Water sources are increasingly threatened by pollution from rapid urbanization, industrial discharge, and agricultural runoff, which introduce harmful contaminants into aquatic ecosystems.Due to their durability, irregular morphology, and possible hazards to the environment and human health, microplastics have become a significant issue among pollutants.A deep learning approach is used to improve the precision and dependability of microplastic identification in microscopic water samples.To address the challenge of detecting microplastics in complex microscopic water images, a Hybrid ROI-Aware Microplastic Detection (HRAMD) framework is proposed.A ResNet-50 FPN backbone is used for feature extraction and bounding box creation in Faster R-CNN for high-resolution droplet photos.The HRAMD method applies Region Of Interest (ROI) refinement to filter out irrelevant background noise, ensuring that only microplastics within the droplet area are considered for analysis.The contamination level is then quantified by calculating the percentage of microplastic area relative to the droplet region, with experimental evaluation yielding an overall average contamination level of 13.13%.This combination of visual bounding box detection and quantitative assessment establishes a transparent and interpretable framework for microplastic monitoring, offering a scalable solution for water quality assessment and sustainable resource management.

Fields of Study & Subjects

Microplastics and Plastic Pollution Advanced Neural Network Applications Remote-Sensing Image Classification

Publication details

Journal / source
Advances in intelligent systems research/Advances in Intelligent Systems Research
Pages
837–847
Publication date
1 April 2026
Language
EN
Document type
Book chapter